Building a predictive machine learning model of gentrification in Sydney

In an era of rapid urbanisation and increasing wealth, gentrification is an urban phenomenon impacting many cities around the world. The ability of policymakers and planners to better understand and address gentrification-induced displacement hinges upon proactive intervention strategies. It is in this context that we build a tree-based machine learning (ML) model to predict neighbourhood change in Sydney. Change, in this context, is proxied by the Socioeconomic Index for Advantage and Disadvantage, in addition to census and other ancillary predictors. Our models predict gentrification from 2011-2016 with a balanced accuracy of 74.7%. Additionally, the use of an additive explanation tool enables individual prediction explanations and advanced feature contribution analysis. Using the ML model, we predict future gentrification in Sydney up to 2021. The predictions confirm that gentrification is expanding outwards from the city centre. A spill-over effect is predicted to the south, west and north-west of former gentrifying hotspots. The findings are expected to provide policymakers with a tool to better forecast where likely areas of gentrification will occur. This future insight can then inform suitable policy interventions and responses in planning for more equitable cities outcomes, specifically for vulnerable communities impacted by gentrification and neighbourhood change.

Differences in Dietary Patterns among the Polish Elderly: A Challenge for Public Health

The aim of the study was to assess the diversity of dietary patterns within the elderly, in relation to the region of residence, household structure, and socioeconomic status. The questionnaire was conducted in a group of 427 Polish adults aged 60 and older from June to September 2019. The sample was selected by means of the snowball method in two regions. Principal component analysis (PCA) was used to extract and identify three dietary patterns (factors) from the frequency of eating 32 groups of foods. Logistic regression analysis was used to determine the relationship between the identified dietary patterns (DPs), region, household status, and socioeconomic index (SES). Adherence to the identified DPs, i.e., traditional, prudent, and adverse, was associated with socioeconomic status (SES) and living environment, i.e., living alone, with partner, or with family, while the region did not differentiate them. Less people living with their family were characterized by the frequent consumption of traditional food (the upper tertile of this DP), while more of them often consumed food that was typical for both prudent and adverse DPs (the upper tertiles of these DPs). The presence of a partner when living with family did not differentiate the adherence to DPs. A high SES decreased the chances of adhering to the upper tertiles of the “prudent” and “traditional” DPs, while living with family increased the chances of adhering to both the upper and middle tertiles of the “prudent” DP. Identifying the dietary patterns of the elderly contributes to a better understanding of the food intake of the senior citizens living in different social situations, in order to support public policies and nutritional counseling among this age group.

Relation of a Socioeconomic Index with Cognitive Function and Neuroimaging in Hypertensive Individuals

Background: Socioeconomic factors are important contributors to brain health. However, data from developing countries (where social inequalities are the most prominent) are still scarce, particularly about hypertensive individuals. Objective: To evaluate the relationship between socioeconomic index, cognitive function, and cortical brain volume, as well as determine whether white matter hyperintensities are mediators of the association of the socioeconomic index with cognitive function in hypertensive individuals. Methods: We assessed 92 hypertensive participants (mean age = 58±8.6 years, 65.2%female). Cognitive evaluation and neuroimaging were performed and clinical and sociodemographic data were collected using questionnaires. A socioeconomic index was created using education, income, occupation (manual or non-manual work), and race. The associations of the socioeconomic index with cognitive performance and brain volume were investigated using linear regression models adjusted for age, sex, time of hypertension since diagnosis, and comorbidities. A causal mediation analysis was also conducted. Results: Better socioeconomic status was associated with better visuospatial ability, executive function, and global cognition. We found associations between a better socioeconomic index and a higher parietal lobe volume. White matter hyperintensities were also not mediators in the relationship between the socioeconomic index and cognitive performance. Conclusion: Socioeconomic disadvantages are associated with worse cognitive performance and brain volume in individuals with hypertension.

A Proposal of Spatial Measurement of Peer Effect through Socioeconomic Indices and Unsatisfied Basic Needs

This paper investigates peer effects in the academic achievement of Costa Rican students. Two measures of peer effects are used: (1) a measure of a schools’ average socioeconomic status and (2) a measure of unsatisfied basic needs at district level. The estimation of a three-level hierarchical model allows us to deal with selection bias and unobserved heterogeneity. Results show that socioeconomic peer effect, both at school and district levels, positively and significantly correlates with academic achievement. An increase in one standard deviation in the socioeconomic index has the same effect on academic achievement as an additional year of schooling; two years if the improvement occurs in the index of unsatisfied basic needs. These results are robust for mathematics, reading and science. Results from quantile regression reveal that students with high academic achievement take greater advantages from studying in schools with higher socioeconomic status (mathematics and reading). Meanwhile, students with low academic achievement are the most affected by studying in poorer districts (mathematics and science).These results show the strong feedback between educational and social inequity and constitute a good example of how poverty traps can persist in developing countries.

Are the effects of air pollution on birth weight modified by infant sex and neighborhood socioeconomic deprivation? A multilevel analysis in Paris (France)

Adverse birth outcomes related to air pollution are well documented; however, few studies have accounted for infant sex. There is also scientific evidence that the neighborhood socioeconomic profile may modify this association even after adjusting for individual socioeconomic characteristics. The objective is to analyze the association between air pollution and birth weight by infant sex and neighborhood socioeconomic index. All birth weights (2008–2011) were geocoded at census block level. Each census block was assigned a socioeconomic deprivation level, as well as daily NO2 and PM10 concentrations. We performed a multilevel model with a multiple statistical test and sensible analysis using the spline function. Our findings suggest the existence of a differential association between air pollution and BW according to both neighborhood socioeconomic level and infant sex. However, due to multiple statistical tests and controlling the false discovery rate (FDR), all significant associations became either not statistically significant or borderline. Our findings reinforce the need for additional studies to investigate the role of the neighborhood socioeconomic which could differentially modify the air pollution effect.

Association of Adult Socioeconomic Status with Body Mass Index: A Within- and Between-Twin Study

Adult socioeconomic status (SES) has been consistently associated with body mass index (BMI), but it is unclear whether it is linked to BMI independently of childhood SES or other potentially confounding factors. Twin studies can address this issue by implicitly controlling for childhood SES and unmeasured confounders. This co-twin control study used cross-sectional data from Twins Research Australia’s Health and Lifestyle Questionnaire (N = 1918 twin pairs). We investigated whether adult SES, as measured by both the Index of Relative Socioeconomic Disadvantage (IRSD) and the Australian Socioeconomic Index 2006 (AUSEI06), was associated with BMI after controlling for factors shared by twins within a pair. The primary analysis was a linear mixed-effects model that estimated effects both within and between pairs. Between pairs, a 10-unit increase in AUSEI06 was associated with a 0.29 kg/m2 decrease in BMI (95% CI [−.42, −.17], p < .001), and a 1-decile increase in IRSD was associated with a 0.26 kg/m2 decrease in BMI (95% CI [−.35, −.17], p < .001). No association was observed within pairs. In conclusion, higher adult SES was associated with lower BMI between pairs, but no association was observed within pairs. Thus, the link between adult SES and BMI may be due to confounding factors common to twins within a pair.

Surname affinity in Santiago, Chile: A network-based approach that uncovers urban segregation

Based on a geocoded registry of more than four million residents of Santiago, Chile, we build two surname-based networks that reveal the city’s population structure. The first network is formed from paternal and maternal surname pairs. The second network is formed from the isonymic distances between the city’s neighborhoods. These networks uncover the city’s main ethnic groups and their spatial distribution. We match the networks to a socioeconomic index, and find that surnames of high socioeconomic status tend to cluster, be more diverse, and occupy a well-defined quarter of the city. The results are suggestive of a high degree of urban segregation in Santiago.

Liver Cancer Incidence and Area-Level Geographic Disparities in Pennsylvania—A Geo-Additive Approach

Many neighborhood socioeconomic index measures (nSES) that capture neighborhood deprivation exist but the impact of measure selection on liver cancer (LC) geographic disparities remains unclear. We introduce a Bayesian geoadditive modeling approach to identify clusters in Pennsylvania (PA) with higher than expected LC incidence rates, adjusted for individual-level factors (age, sex, race, diagnosis year) and compared them to models with 7 different nSES index measures to elucidate the impact of nSES and measure selection on LC geospatial variation. LC cases diagnosed from 2007–2014 were obtained from the PA Cancer Registry and linked to nSES measures from U.S. census at the Census Tract (CT) level. Relative Risks (RR) were estimated for each CT, adjusted for individual-level factors (baseline model). Each nSES measure was added to the baseline model and changes in model fit, geographic disparity and state-wide RR ranges were compared. All 7 nSES measures were strongly associated with high risk clusters. Tract-level RR ranges and geographic disparity from the baseline model were attenuated after adjustment for nSES measures. Depending on the nSES measure selected, up to 60% of the LC burden could be explained, suggesting methodologic evaluations of multiple nSES measures may be warranted in future studies to inform LC prevention efforts.

ANÁLISIS DE RESULTADOS DEL EXAMEN SER BACHILLER EN EL DOMINIO MATEMÁTICO

El examen Ser Bachiller (2016) es un instrumento que evalúa las destrezas y aptitudes del postulante con la finalidad de obtener el título de bachiller y contar con un cupo en las instituciones de educación superior en el Ecuador. Por otro lado, el dominio matemático desarrolla múltiples habilidades que ayudan a afrontar diversas situaciones en la vida real; sin embargo, los datos demuestran que en este dominio los estudiantes tienen menor puntuación. Por esta razón, el objetivo de la presente investigación es analizar la correlación entre el puntaje del dominio matemático con el tipo de sostenimiento de las instituciones educativas (IE) en que el estudiante cursó sus estudios secundarios y la segregación de la población por el índice socioeconómico; adicionalmente, se busca las mejores puntuaciones en dicho dominio por la ubicación geográfica. Para el logro de los objetivos se utilizó la base de datos proporcionada por el Instituto Nacional de Evaluación Educativa en su sitio web oficial de los períodos 2016-2017, 2017-2018 y 2018-2019 mediante un análisis exploratorio y filtración de los datos. Como resultado se obtuvo que existen diferencias significativas del puntaje del dominio matemático con el tipo de sostenimiento de las IE y el índice socioeconómico respectivamente; además, las puntuaciones más altas en los tres períodos de estudios se encuentran en la provincia de Tungurahua. Como conclusión los estudiantes de instituciones educativas municipales y particulares obtienen mejores puntuaciones en el dominio matemático, al igual de aquellos que pertenecen al quintil 5 (población más pudiente), por otro lado, en la provincia de Tungurahua, y sus cantones de Pelileo, Quero y Cevallos fueron los que sacaron las mejores puntuaciones en este dominio matemático en los 3 años consecutivos. PALABRAS CLAVE: Ser Bachiller; dominio matemático; tipo de sostenimiento; índice socioeconómico; ubicación geográfica. ANALYSIS OF RESULTS OF THE SER BACHILLER EXAM IN THE MATHEMATICAL DOMAIN ABSTRACT The Ser Bachiller exam (2016) is an instrument that evaluates the skills and aptitudes of the applicant in order to obtain the bachelor's degree and have a quota for higher education institutions. On the other hand, the mathematical domain develops several skills that help to face different situations in real life, however, the data show that in this domain the students have lower scores. For this reason, the objective of this research is to analyze the correlation between the mathematical proficiency score with the type of support of the educational institutions in which the student attended secondary school and the segregation of the population by the socioeconomic index; Additionally, the best scores in that domain are searched for by geographic location. For the achievement of the objectives, the database provided on the official website of the National Institute for Educational Evaluation for the periods 2016-2017, 2017-2018 and 2018-2019 was used through an exploratory analysis and data filtration. As a result, it was obtained that there are significant differences in the mathematical proficiency score with the type of EI support and the socioeconomic index respectively, and the highest scores in the three study periods are found in the province of Tungurahua. In conclusion, students from municipal and private educational institutions obtain better scores in the mathematical domain, as well as those who belong to quintile 5 (the wealthiest population), on the other hand, in the parishes of Tungurahua there are better scores in this domain. KEYWORDS: Ser Bachiller; mathematical domain type of support; socioeconomic index; geographic location.